Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Kłosowski, Grzegorz; Rymarczyk, Tomasz; Kania, Konrad; Świć, Antoni; Cieplak, Tomasz

doi:10.17531/ein.2020.1.16

Cited by 52 publications

(37 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the same way, the algorithm selected is classical and needs to be considered in any benchmark. Advanced modern algorithms using machine learning can be considered as a comparison, for example, Bayesian learning [ 42 , 43 ] or neural networks [ 8 , 44 ]. A comparative analysis of reconstruction strategy, excitation configuration and waveform modulation is part of further work in preparation.…”

Section: Resultsmentioning

confidence: 99%

“…The latter can be tracked considering the changes in lung impedance via electrical tomography [ 3 , 4 ]. There are many tomographic solutions and methods for analyzing measurements or reconstructing images [ 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 , 13 ], sharing the fundamental principles but varying in the perturbation type, the surface information sensed, the geometry of the problem and the dynamics characteristics of the image reconstruction process. Moderate to low energy tomographic techniques are important for the future of medical imaging, especially for safe in vivo data acquisition and for prolonged continuous monitoring.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Electrical Tomography Reconstruction Using Reconfigurable Waveforms in a FPGA

Vejar

Rymarczyk

2021

Sensors

Self Cite

View full text Add to dashboard Cite

The principal objective of this research is to conceive a mobile system based on electrical tomography for subsurface imaging and monitoring in order to enable simultaneous recording of electrical potentials of cardiac and pulmonary activity. For an exploration of excitation waveforms in electrical tomography, specialized hardware is required. As the main principle of tomography is the measurement of electrical perturbations on an unknown object, it is crucial to synchronize excitation and sensing processes in a very precise way for the purpose of acquiring meaningful data. To cope with this problem, an FPGA device is used, with an architecture that allows us to trigger excitation signals and to read sensed data simultaneously via independent processes that share the same clock. In this way, waveform reconfiguration on frequency and shape can be provided and studied. The system is connected to a standard microcontroller SoC with a simple API that allows for IoT capabilities for on-line operation and tracking, given that the design is targeted for in vivo medical monitoring. As a result of the research work, a measuring device was developed, the surface data analyzed and the image was reconstructed using the selected configuration.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Electrical Tomography Reconstruction Using Reconfigurable Waveforms in a FPGA

Vejar

Rymarczyk

2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…where N c denotes the number of pixels reconstructed correctly and N denotes the total number of pixels [50]. Cross entropy loss between network predictions and target values is defined as Equation (13).…”

Section: Lstm With a Singular Raw Ecg Signal Inputmentioning

confidence: 99%

The Use of Time-Frequency Moments as Inputs of LSTM Network for ECG Signal Classification

Kłosowski

Rymarczyk

Wójcik³

et al. 2020

Electronics

Self Cite

View full text Add to dashboard Cite

This paper refers to the method of using the deep neural long-short-term memory (LSTM) network for the problem of electrocardiogram (ECG) signal classification. ECG signals contain a lot of subtle information analyzed by doctors to determine the type of heart dysfunction. Due to the large number of signal features that are difficult to identify, raw ECG data is usually not suitable for use in machine learning. The article presents how to transform individual ECG time series into spectral images for which two characteristics are determined, which are instantaneous frequency and spectral entropy. Feature extraction consists of converting the ECG signal into a series of spectral images using short-term Fourier transformation. Then the images were converted using Fourier transform again to two signals, which includes instantaneous frequency and spectral entropy. The data set transformed in this way was used to train the LSTM network. During the experiments, the LSTM networks were trained for both raw and spectrally transformed data. Then, the LSTM networks trained in this way were compared with each other. The obtained results prove that the transformation of input signals into images can be an effective method of improving the quality of classifiers based on deep learning.

show abstract

“…To assess the quality and correctness of the production process, both at the production stage and in the operational control phase, preference is given to non-invasive diagnostic methods -the so-called non-destructive testing. Such methods include, among others tomography (electric, ultrasound, magnetic) Rymarczyk, Kozłowski, Kłosowski, and Niderla, 2019;Kłosowski et al, 2020), electromagnetic testing or eddy current method (Li et al, 2021), visual research method (Deng et al, 2018), penetration method (Kryukov et al, 2016) or magnetic method (Tönshoff, Karpuschewski, and Regent, 1999). The main directions of the use of the eddy current method are the detection of material defects -defectoscopy, testing of material properties -structroscopy and the determination of dimensions (mainly thickness measurements).…”

Section: Introductionmentioning

confidence: 99%

The Use of Transfer Learning with Very Deep Convolutional Neural Network in Quality Management

Kłosowski¹,

Kulisz²,

Lipski³

et al. 2021

ERSJ

Self Cite

View full text Add to dashboard Cite

The aim of the article is to develop an algorithm for classifying cracks in the analyzed images using modern methods of deep machine learning and transfer learning based on pretrained convolutional neural network -Inception-ResNet-v2. Design/Methodology/Approach: Transfer learning based on the pretrained convolutional neural network was used to categorize the images. The fully conected layer of the Inception-ResNet-v2 network has been modified. The last layer was trained using a two-class (binary) linear SVM (Support Vector Machine). In total, 20,000 training cases (images) were used to train the fully connected layer within transfer learning process. The research analyzed the possibility of using the deep neural networks for quick and fully automatic identification of cracks / defects on the surface of analyzed parts. Findings:The results indicate that pretrained convolutional neural network using SVM to train a fully connected layer is a very effective solution for visual crack / fault detection. In the analyzed model, a positive classification was obtained at the level of 99.89%. Practical Implications: The model presented in the article can be used in quality control carried out by process monitoring. An effective model for identifying defective parts can be used in both logistics and production processes. Originality/Value: A novelty is the use of a freely available, deep neural network trained to classify 1000 categories of various images for binary categorization of faults (cracks). The algorithm was adjusted by replacing the primary, 1000-output fully connected layer in the Inception-ResNet-v2 network with a binary layer (2 categories). The fully connected layer has been trained using the classification version of the popular SVM learner, but thanks to the combination of this layer with the sophisticated fearure extraction ability of the pre-trained Inception-ResNet-v2 deep network, the resulting predictive model enables the classification of defects with a very high level of accuracy.

show abstract

Maintenance of industrial reactors supported by deep learning driven ultrasound tomography

Cited by 52 publications

References 39 publications

Electrical Tomography Reconstruction Using Reconfigurable Waveforms in a FPGA

Electrical Tomography Reconstruction Using Reconfigurable Waveforms in a FPGA

The Use of Time-Frequency Moments as Inputs of LSTM Network for ECG Signal Classification

The Use of Transfer Learning with Very Deep Convolutional Neural Network in Quality Management

Contact Info

Product

Resources

About